Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    teacher

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loud
    -0.07
     Digital
    -0.07
     sage
    -0.06
    重複重複
    -0.06
     Challenges
    -0.06
    .accounts
    -0.06
    ιών
    -0.06
     Brut
    -0.06
     charitable
    -0.06
     đồ
    -0.06
    POSITIVE LOGITS
    _GO
    0.07
     kendisi
    0.07
     expand
    0.07
     نیم
    0.07
    Es
    0.07
     PKK
    0.06
    .pointer
    0.06
    leaning
    0.06
    -flag
    0.06
    .cards
    0.06
    Act Density 0.008%

    No Known Activations